Adaptive Methods papers, 2023–2026

Key findings

• Adaptive Methods went from 143 papers in 2023 to 410 in 2026, roughly 2.9x in three years.
• NeurIPS publishes the most Adaptive Methods work: 365 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Theory · optimization: papers tagged with both rose from 1 in 2023 to 29 in 2026.
• Among the 5 topics under Optimization and Scaling, it ranks #3 by 2026 paper count; the fastest grower in the group, Scaling Laws, is up 4.1x versus 2.9x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026AcceleGrad#: Adaptive Geometry-Aware Acceleration
• ICML 2026Adaptive Bandit Algorithms for Contextual Matching Markets
• ICLR 2026Adaptive Width Neural Networks
• CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
• NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
• ICML 2025Adaptive Data Collection for Robust Learning Across Multiple Distributions
• ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
• CVPR 2025A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
• NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
• ICML 2024A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
• ICLR 2024Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
• CVPR 2024HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
• NeurIPS 2023A Bounded Ability Estimation for Computerized Adaptive Testing
• ICML 2023A/B Testing in Network Data with Covariate-Adaptive Randomization
• ICLR 2023An Adaptive Policy to Employ Sharpness-Aware Minimization
• CVPR 2023Adaptive Annealing for Robust Geometric Estimation
• NeurIPS 2026AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
• ICML 2026Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
• ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks

All Adaptive Methods papers

410 papers, page 5 of 9

201. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
202. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?
203. ICML 2026CARE: Adaptive Calibration for Reliable Recommendations
204. ICML 2026CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
205. ICML 2026Cold-Start Personalization via Bayesian Adaptive Questioning
206. ICML 2026Constrained Adaptive Rejection Sampling
207. ICML 2026Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
208. ICML 2026Data-Source Adaptive Online Learning under Heteroscedastic Noise
209. ICML 2026Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
210. ICML 2026Delving into Muon and Beyond: Deep Analysis and Extensions
211. ICML 2026DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
212. ICML 2026dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
213. ICML 2026Domain Adaptive Object Detection via Dynamic Causal Refinement
214. ICML 2026DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
215. ICML 2026Dual-channel Dynamic Graph Neural Networks with Adaptive Adjacency Learning and Multi-scale Representation Fusion
216. ICML 2026DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
217. ICML 2026Entropic Mirror Monte Carlo
218. ICML 2026Entropy-informed Decoding: Adaptive Information-Driven Branching
219. ICML 2026FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning
220. ICML 2026FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
221. ICML 2026Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive Damping
222. ICML 2026Geometry-Misalignment in Distributional Learning
223. ICML 2026Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
224. ICML 2026GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
225. ICML 2026GradientStabilizer: Fix the Norm, Not the Gradient
226. ICML 2026HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
227. ICML 2026HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
228. ICML 2026Identifiable Nonlinear Differentiable Causal Discovery via Independence and Adaptive Group Sparsity
229. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
230. ICML 2026JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
231. ICML 2026KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
232. ICML 2026LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
233. ICML 2026Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction
234. ICML 2026Learning Adaptive Topology with FiLM-Guided Distillation for Tertiary Structure-Based RNA Design
235. ICML 2026LoRe: Adaptive Interaction-Evaluation Routing with Per-step Interaction Budgets for Iterative Graph Solvers
236. ICML 2026M+Adam: Low-Precision Training via Additive–Multiplicative Optimization
237. ICML 2026Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
238. ICML 2026MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
239. ICML 2026MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
240. ICML 2026Model-Preserving Adaptive Rounding
241. ICML 2026Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint Decomposition
242. ICML 2026Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain Generalization
243. ICML 2026Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
244. ICML 2026Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting
245. ICML 2026OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
246. ICML 2026PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$
247. ICML 2026PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
248. ICML 2026Preconditioning Neural Tangent Kernel for Adaptive Optimization
249. ICML 2026Prediction-Powered Adaptive Inference with Pretrained AI Models for Contextual Bandits
250. ICML 2026PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training

FAQ

How many Adaptive Methods papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,012 in total: 143 in 2023, 183 in 2024, 276 in 2025, 410 in 2026.

How many Adaptive Methods papers are at NeurIPS 2026?

NeurIPS 2026 has 138 Adaptive Methods papers, versus 109 the year before.

How many Adaptive Methods papers are at ICLR 2026?

ICLR 2026 has 80 Adaptive Methods papers, versus 47 the year before.

How many Adaptive Methods papers are at ICML 2026?

ICML 2026 has 109 Adaptive Methods papers, versus 68 the year before.

How many Adaptive Methods papers are at CVPR 2026?

CVPR 2026 has 83 Adaptive Methods papers, versus 52 the year before.

Which conference publishes the most Adaptive Methods papers?

NeurIPS, with 365 papers from 2023 to 2026.